
GenAI in SnapApp
on 07-17-2024 12:00 AM by SnapApp by BlueVector AI
640
Generative AI (GenAI) is a subset of artificial intelligence focused on creating new content, such as text/text summaries, images, audio, video, or code based on the collective knowledge acquired from a Large Language Model (LLM) and, importantly, grounded in the specific data you desire including Websites, GCS Buckets, REST APIs, Cloud SQL dbs, Google Drive and of course documents and data stored in SnapApp. It can can be used to generate comments, determination, and replies. It can also summarize documents and search them using human-like queries. It can also be used to generate code snippets, documents, presentations, images, audio and video files.
Table of Contents
- GenAI in SnapApp
- Generate Text in Text Fields
- Generate Text in Pages
- Generate Text in Expression
- Generate Text with Image in Expression
- Generate Images in Fields
- Generate Images in Pages
- Generate Images in Expression
GenAI in SnapApp
Further, to meet your transparency/disclosure policy guidelines, you can enable Generative AI Disclosure Notifications and set an AI disclosure message that will appear wherever GenAI features appear in the app.
You can also use GenAI in SnapApp to:
- Generate Records
- Generate Child Records
- Generate Slides
- Generate Documents
- Generate Custom Functions
- Generate Expressions
- Generative Search
-
Generative Document Search
-
Text and Image Generation using Generative AI
Generate Text in Text Fields
You can give your users the specify a prompt to automatically generate text in any Text or LongText field. To simplify this you can even create a formula to create the initial prompt that the user can then modify to suit their needs.
For instance, let’s say you have created an object to store products. This object has a field for name, type, and description. You could create a prompt formula on the description field like this “=Create a professional product description in 50 words or less of a [[type]] product called [[name]] that can be used on website and marketing material”. This can accelerate the Generate text by providing prompt message in case of Text and Long Text fields.
Generate Text in Pages
You can automatically generate text for your SnapApp pages. This is useful to quickly add text-based content to a page. To do this, select an existing typography block or drop a new typography block from the component panel (select + icon on top right) on to the page. Once the typography block is selected, click the settings cog. From the settings cog you can generate text using the “Full Generate Text” button which will open a modal with a set of parameters for text creations or the “Generate Text” button which will allow you to create a freeform prompt to generate new text.
Generate Text in Expression
Generate text by providing expression function (GENERATE_TEXT()) from expression builder.
Generate Text with Image in Expression
Generate text by providing expression function (GENERATE_TEXT_WITH_IMAGE()) from expression builder.
Generate Images in Fields
Generate image by providing prompt message in case of changing input in image field.
Generate Images in Pages
You can automatically generate images for your SnapApp pages. This is useful to quickly add graphic-based content to a page. To do this, select an existing image block or drop a new image block from the component panel (select + icon on top right) on to the page. Once the images block is selected, click the settings cog. From the settings cog you can generate text using the “Generate Image” button which will open a modal with a set of parameters for image creation.
Generate Images in Expression
Generate image by providing expression function (GENERATE_IMAGE()) from expression builder.
- Feeds using Generative AI (in peek view)
Feature | Description | Model Used |
---|---|---|
Generative Summary | Context-based generative summary of the conversation. | Text-unicorn model (supports 32000 tokens) |
Feed Autocomplete | Context-based auto-complete of reply, directly into the text-box | Text-unicorn model |
Quick reply options | Context-based user aware quick reply options on actual valuable context. | Text-unicorn models |
In the above example, a summary of the conversation and relevant automatic feed is generated using GenAI.
- Generative Search (Native)
Generative search (native) is a GenAI driven search tool, which works by creating SQL select queries by understanding the question and also provide insights about the retrieved data.
It is SnapApp’s own generative search using GenAI features in the framework of SnapApp’s own IP and integrated with SnapApp. It uses Gemini-1.5-flash to query that supports one million tokens, gather insights and form answer to the questions. It is suitable for data related queries, filtering, sorting, doing aggregation and schema-based queries but does not support keyword-related search. It does not pass all the data into the model rather than only the resultant data set received from SQL Query.
In the above example, a summary of the anime with maximum episodes is searched, and on the basis of table records of SnapApp, it searched the appropriate record and produce the summary.
- Generative Search (Agent Builder)
Generative search Plus is a tool that uses google’s search and conversation API to create a datastore and answers question from the datastore.
It is a vector search which supports keyword related searches but unable to filter, sort and provide answers to schema-based questions.
To use this, you have to upload the table data to Google’s data store, then after populating those data, you can search. It basically search for the top 5 most relevant similar meaning word and in addition it produces the generative summary of the answer(preview feature).
The above example shows the top 5 related search with a general summary of the question, and each time you refresh, the summary will be changed.
- Document Search (Agent Builder)
DocSearch leverages Google’s search and conversation capabilities to sift through document content and stored within SnapApp.
It produces a summarized answer to the question along with proper documents and relevant snippets for supportive data reference. Tapping on the summary will open the relevant page of the document. This result also includes the record of the SnapApp and the supported documents.
In the above example, a relevant summary is generated on the basis of the question with relevant refential citations for the data.
Thank you for following these steps to configure your SnapApp components effectively If you have any questions or need further assistance, please don’t hesitate to reach out to our support team. We’re here to help you make the most out of your SnapApp experience.
For support, email us at snapapp@bluevector.ai